Phi-2_MoE_test / model.safetensors.index.json
AbstractPerspective's picture
Upload PhiForCausalLM
5fc51c6 verified
{
"metadata": {
"total_size": 8915957760
},
"weight_map": {
"lm_head.linear.bias": "model-00002-of-00002.safetensors",
"lm_head.linear.weight": "model-00002-of-00002.safetensors",
"lm_head.ln.bias": "model-00002-of-00002.safetensors",
"lm_head.ln.weight": "model-00002-of-00002.safetensors",
"transformer.embd.wte.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.0.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.0.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.0.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.0.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.0.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.0.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.1.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.1.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.1.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.1.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.1.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.1.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.10.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.10.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.10.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.10.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.10.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.10.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.11.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.11.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.11.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.11.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.11.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.11.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.12.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.12.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.12.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.12.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.12.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.12.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.13.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.13.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.13.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.13.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.13.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.13.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.14.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.14.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.14.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.14.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.14.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.14.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.14.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.14.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.15.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.15.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.15.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.15.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.15.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.15.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.15.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.16.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.16.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.16.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.16.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.16.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.16.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.16.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.16.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.17.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.17.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.17.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.17.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.17.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.17.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.17.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.17.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.17.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.17.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.17.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.17.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.17.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.17.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.18.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.18.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.18.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
"transformer.h.18.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
"transformer.h.18.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.moe.gate.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.moe.mlp.0.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.18.moe.mlp.0.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.moe.mlp.0.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.18.moe.mlp.0.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.moe.mlp.1.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.18.moe.mlp.1.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.18.moe.mlp.1.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.18.moe.mlp.1.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.ln.bias": "model-00002-of-00002.safetensors",
"transformer.h.19.ln.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
"transformer.h.19.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
"transformer.h.19.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.moe.gate.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.moe.mlp.0.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.19.moe.mlp.0.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.moe.mlp.0.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.19.moe.mlp.0.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.moe.mlp.1.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.19.moe.mlp.1.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.19.moe.mlp.1.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.19.moe.mlp.1.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.2.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.2.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.2.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.2.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.2.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.2.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.2.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.20.ln.bias": "model-00002-of-00002.safetensors",
"transformer.h.20.ln.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
"transformer.h.20.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
"transformer.h.20.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.moe.gate.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.moe.mlp.0.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.20.moe.mlp.0.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.moe.mlp.0.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.20.moe.mlp.0.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.moe.mlp.1.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.20.moe.mlp.1.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.20.moe.mlp.1.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.20.moe.mlp.1.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.ln.bias": "model-00002-of-00002.safetensors",
"transformer.h.21.ln.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
"transformer.h.21.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
"transformer.h.21.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.moe.gate.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.moe.mlp.0.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.21.moe.mlp.0.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.moe.mlp.0.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.21.moe.mlp.0.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.moe.mlp.1.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.21.moe.mlp.1.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.21.moe.mlp.1.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.21.moe.mlp.1.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.ln.bias": "model-00002-of-00002.safetensors",
"transformer.h.22.ln.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
"transformer.h.22.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
"transformer.h.22.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.moe.gate.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.moe.mlp.0.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.22.moe.mlp.0.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.moe.mlp.0.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.22.moe.mlp.0.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.moe.mlp.1.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.22.moe.mlp.1.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.22.moe.mlp.1.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.22.moe.mlp.1.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.ln.bias": "model-00002-of-00002.safetensors",
"transformer.h.23.ln.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
"transformer.h.23.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
"transformer.h.23.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.moe.gate.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.moe.mlp.0.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.23.moe.mlp.0.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.moe.mlp.0.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.23.moe.mlp.0.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.moe.mlp.1.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.23.moe.mlp.1.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.23.moe.mlp.1.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.23.moe.mlp.1.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.24.ln.bias": "model-00002-of-00002.safetensors",
"transformer.h.24.ln.weight": "model-00002-of-00002.safetensors",
"transformer.h.24.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
"transformer.h.24.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
"transformer.h.24.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
"transformer.h.24.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.24.moe.gate.weight": "model-00002-of-00002.safetensors",
"transformer.h.24.moe.mlp.0.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.24.moe.mlp.0.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.24.moe.mlp.0.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.24.moe.mlp.0.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.24.moe.mlp.1.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.24.moe.mlp.1.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.24.moe.mlp.1.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.24.moe.mlp.1.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.25.ln.bias": "model-00002-of-00002.safetensors",
"transformer.h.25.ln.weight": "model-00002-of-00002.safetensors",
"transformer.h.25.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
"transformer.h.25.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
"transformer.h.25.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
"transformer.h.25.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.25.moe.gate.weight": "model-00002-of-00002.safetensors",
"transformer.h.25.moe.mlp.0.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.25.moe.mlp.0.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.25.moe.mlp.0.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.25.moe.mlp.0.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.25.moe.mlp.1.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.25.moe.mlp.1.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.25.moe.mlp.1.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.25.moe.mlp.1.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.26.ln.bias": "model-00002-of-00002.safetensors",
"transformer.h.26.ln.weight": "model-00002-of-00002.safetensors",
"transformer.h.26.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
"transformer.h.26.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
"transformer.h.26.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
"transformer.h.26.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.26.moe.gate.weight": "model-00002-of-00002.safetensors",
"transformer.h.26.moe.mlp.0.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.26.moe.mlp.0.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.26.moe.mlp.0.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.26.moe.mlp.0.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.26.moe.mlp.1.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.26.moe.mlp.1.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.26.moe.mlp.1.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.26.moe.mlp.1.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.27.ln.bias": "model-00002-of-00002.safetensors",
"transformer.h.27.ln.weight": "model-00002-of-00002.safetensors",
"transformer.h.27.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
"transformer.h.27.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
"transformer.h.27.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
"transformer.h.27.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.27.moe.gate.weight": "model-00002-of-00002.safetensors",
"transformer.h.27.moe.mlp.0.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.27.moe.mlp.0.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.27.moe.mlp.0.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.27.moe.mlp.0.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.27.moe.mlp.1.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.27.moe.mlp.1.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.27.moe.mlp.1.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.27.moe.mlp.1.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.28.ln.bias": "model-00002-of-00002.safetensors",
"transformer.h.28.ln.weight": "model-00002-of-00002.safetensors",
"transformer.h.28.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
"transformer.h.28.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
"transformer.h.28.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
"transformer.h.28.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.28.moe.gate.weight": "model-00002-of-00002.safetensors",
"transformer.h.28.moe.mlp.0.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.28.moe.mlp.0.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.28.moe.mlp.0.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.28.moe.mlp.0.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.28.moe.mlp.1.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.28.moe.mlp.1.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.28.moe.mlp.1.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.28.moe.mlp.1.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.29.ln.bias": "model-00002-of-00002.safetensors",
"transformer.h.29.ln.weight": "model-00002-of-00002.safetensors",
"transformer.h.29.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
"transformer.h.29.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
"transformer.h.29.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
"transformer.h.29.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.29.moe.gate.weight": "model-00002-of-00002.safetensors",
"transformer.h.29.moe.mlp.0.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.29.moe.mlp.0.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.29.moe.mlp.0.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.29.moe.mlp.0.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.29.moe.mlp.1.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.29.moe.mlp.1.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.29.moe.mlp.1.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.29.moe.mlp.1.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.3.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.3.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.3.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.3.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.3.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.3.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.3.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.30.ln.bias": "model-00002-of-00002.safetensors",
"transformer.h.30.ln.weight": "model-00002-of-00002.safetensors",
"transformer.h.30.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
"transformer.h.30.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
"transformer.h.30.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
"transformer.h.30.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.30.moe.gate.weight": "model-00002-of-00002.safetensors",
"transformer.h.30.moe.mlp.0.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.30.moe.mlp.0.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.30.moe.mlp.0.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.30.moe.mlp.0.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.30.moe.mlp.1.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.30.moe.mlp.1.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.30.moe.mlp.1.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.30.moe.mlp.1.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.31.ln.bias": "model-00002-of-00002.safetensors",
"transformer.h.31.ln.weight": "model-00002-of-00002.safetensors",
"transformer.h.31.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
"transformer.h.31.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
"transformer.h.31.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
"transformer.h.31.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
"transformer.h.31.moe.gate.weight": "model-00002-of-00002.safetensors",
"transformer.h.31.moe.mlp.0.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.31.moe.mlp.0.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.31.moe.mlp.0.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.31.moe.mlp.0.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.31.moe.mlp.1.fc1.bias": "model-00002-of-00002.safetensors",
"transformer.h.31.moe.mlp.1.fc1.weight": "model-00002-of-00002.safetensors",
"transformer.h.31.moe.mlp.1.fc2.bias": "model-00002-of-00002.safetensors",
"transformer.h.31.moe.mlp.1.fc2.weight": "model-00002-of-00002.safetensors",
"transformer.h.4.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.4.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.4.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.4.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.4.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.4.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.4.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.4.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.5.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.5.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.5.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.5.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.5.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.5.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.5.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.6.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.6.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.6.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.6.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.6.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.6.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.6.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.7.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.7.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.7.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.7.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.7.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.7.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.7.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.8.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.8.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.8.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.8.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.8.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.8.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.8.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.ln.bias": "model-00001-of-00002.safetensors",
"transformer.h.9.ln.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
"transformer.h.9.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
"transformer.h.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.moe.gate.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.moe.mlp.0.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.9.moe.mlp.0.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.moe.mlp.0.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.9.moe.mlp.0.fc2.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.moe.mlp.1.fc1.bias": "model-00001-of-00002.safetensors",
"transformer.h.9.moe.mlp.1.fc1.weight": "model-00001-of-00002.safetensors",
"transformer.h.9.moe.mlp.1.fc2.bias": "model-00001-of-00002.safetensors",
"transformer.h.9.moe.mlp.1.fc2.weight": "model-00001-of-00002.safetensors"
}
}